Reading an article about ELO rank I have a question. The probability of the "A" team win is a sigmoid function like 1 / (1 + exp( RankB -RankA))
and after the game we need to update these ranks like Rank_new = Rank_old +- K*(1(0) - probability)
So the main question is how I can use for example NN( or other algo) for finding "K" parameter to make binary crossentropy minimum. And I hope it musn't be constant (I want to find dependent from the initial player rating)
The main my problem that I can't understand is that we need after updating parameters use a new input rank for calculating probability. So every epoch we need to update input
I think your best bet is to use Genetic Algorithms (GA) if you are trying to find the optimum value of K;the link above should take you to a sample GA code provided by Will Larson.